© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 19260
    Prev
    Next
    INDEX
    Explanations

    words related to different sides or aspects of a situation or object

    oai_token-act-pair · gpt-3.5-turbo

    references to different aspects or sides of a topic or situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ruary
    -0.76
    urated
    -0.74
    reditary
    -0.68
    incinn
    -0.63
    redo
    -0.62
    uilding
    -0.62
    arus
    -0.62
    Tips
    -0.60
    rely
    -0.60
    astical
    -0.58
    POSITIVE LOGITS
    atics
    0.70
     thereof
    0.68
    uctions
    0.67
    ials
    0.62
    naires
    0.62
    umption
    0.58
    UCT
    0.57
    ality
    0.57
     of
    0.56
    ibles
    0.55
    Activations Density 0.380%

    No Known Activations